AHupuJR
Release REFID checkpoints and HighREV dataset on Hugging Face
Hi @AHupuJR 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work on Arxiv and was wondering whether you would like to submit it to hf.co/papers to improve its discoverability. If you are one of the authors, you can submit it at https://huggingface.co/papers/submit.
The paper page lets people discuss about your paper and lets them find artifacts about it, and also claim the paper as yours which will show up on your public profile at HF.
I noticed that you've released the code and weights for REFID, as well as introduced the HighREV dataset. It would be great to have these artifacts on the Hugging Face Hub as well to improve discoverability.
We can host the following checkpoints on the Hub:
- REFID-GoPro-11-1
- REFID-GoPro-11-3
- REFID-GoPro-7skip
- REFID-GoPro-15skip
- REFID-GoPro-single-deblur
- REFID-HighREV-1skip
- REFID-HighREV-3skip
- REFID-HighREV-7skip
- REFID-HighREV-15skip
- REFID-HighREV-single-deblur
See here for a guide: https://huggingface.co/docs/hub/models-uploading. In this case, we could leverage the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to any custom nn.Module. Alternatively, one can leverage the hf_hub_download one-liner to download a checkpoint from the hub. We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.
Would be awesome to make the dataset available on 🤗, so that people can do:
from datasets import load_dataset
dataset = load_dataset("your-hf-org-or-username/your-dataset")
See here for a guide: https://huggingface.co/docs/datasets/loading.
I also understand that dataset download is allowed only with the authority of Alpsentek. We can add a note in the dataset card mentioning that download requires contacting Alpsentek.
Let me know if you're interested/need any help regarding this!
Cheers, Niels
